PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
Matthias Rupp, Alexandre Tkatchenko, Klaus-Robert Müller and O. Anatole von Lilienfeld
Physical Review Letters Volume 108, Number 5, 058301, 2012. ISSN 1079-7114

Abstract

We introduce a machine learning model to predict atomization energies of a diverse set of organic molecules, based on nuclear charges and atomic positions only. The problem of solving the molecular Schrödinger equation is mapped onto a nonlinear statistical regression problem of reduced complexity. Regression models are trained on and compared to atomization energies computed with hybrid density-functional theory. Cross validation over more than seven thousand organic molecules yields a mean absolute error of ∼10  kcal/mol. Applicability is demonstrated for the prediction of molecular atomization potential energy curves.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
ID Code:9418
Deposited By:Matthias Rupp
Deposited On:16 March 2012